[Qemu-devel] [PATCH COLO-Frame v7 19/34] COLO failover: Don't do failover during loading VM's state

[zhanghailiang <zhang.zhanghailiang@huawei.com>]

We should not do failover work while the main thread is loading
VM's state, otherwise it will destroy the consistent of VM's memory and
device state.

Here we add a new failover status 'RELAUNCH' which means we should
relaunch the process of failover.

Signed-off-by: zhanghailiang <zhang.zhanghailiang@huawei.com>
Signed-off-by: Li Zhijian <lizhijian@cn.fujitsu.com>
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
---
 include/migration/failover.h |  2 ++
 migration/colo.c             | 22 ++++++++++++++++++++++
 2 files changed, 24 insertions(+)

diff --git a/include/migration/failover.h b/include/migration/failover.h
index f85f97d..3f65f5d 100644
--- a/include/migration/failover.h
+++ b/include/migration/failover.h
@@ -20,6 +20,8 @@ typedef enum COLOFailoverStatus {
     FAILOVER_STATUS_REQUEST = 1, /* Request but not handled */
     FAILOVER_STATUS_HANDLING = 2, /* In the process of handling failover */
     FAILOVER_STATUS_COMPLETED = 3, /* Finish the failover process */
+    /* Optional, Relaunch the failover process, again 'NONE' -> 'COMPLETED' */
+    FAILOVER_STATUS_RELAUNCH = 4,
 } COLOFailoverStatus;
 
 int failover_set_state(int old_state, int new_state);
diff --git a/migration/colo.c b/migration/colo.c
index 70fcf25..aab7b38 100644
--- a/migration/colo.c
+++ b/migration/colo.c
@@ -53,6 +53,7 @@ enum {
 };
 
 static QEMUBH *colo_bh;
+static bool vmstate_loading;
 static Coroutine *colo;
 /* colo buffer */
 #define COLO_BUFFER_BASE_SIZE (4 * 1024 * 1024)
@@ -90,6 +91,18 @@ static bool colo_runstate_is_stopped(void)
 static void secondary_vm_do_failover(void)
 {
     int old_state;
+    /* Can not do failover during the process of VM's loading VMstate, Or
+      * it will break the secondary VM.
+      */
+    if (vmstate_loading) {
+        old_state = failover_set_state(FAILOVER_STATUS_HANDLING,
+                                       FAILOVER_STATUS_RELAUNCH);
+        if (old_state != FAILOVER_STATUS_HANDLING) {
+            error_report("Unknow error while do failover for secondary VM,"
+                         "old_state: %d", old_state);
+            return;
+        }
+    }
 
     /* It means that VM exit from COLO state */
     colo = NULL;
@@ -528,13 +541,22 @@ void *colo_process_incoming_checkpoints(void *opaque)
 
         qemu_mutex_lock_iothread();
         qemu_system_reset(VMRESET_SILENT);
+        vmstate_loading = true;
         if (qemu_loadvm_state(fb) < 0) {
             error_report("COLO: loadvm failed");
+            vmstate_loading = false;
             qemu_mutex_unlock_iothread();
             goto out;
         }
+
+        vmstate_loading = false;
         qemu_mutex_unlock_iothread();
 
+        if (failover_get_state() == FAILOVER_STATUS_RELAUNCH) {
+            failover_set_state(FAILOVER_STATUS_RELAUNCH, FAILOVER_STATUS_NONE);
+            failover_request_active(NULL);
+            goto out;
+        }
         ret = colo_ctl_put(ctl, COLO_CHECKPOINT_LOADED);
         if (ret < 0) {
             goto out;
-- 
1.7.12.4